System and method for preventing locked axle

Abstract

To solve the problem of causing a loss of revenue while disrupting traffic of a rail system.SOLUTION: Methods are provided which may include determining one or more of a vibration characteristic and a fluid characteristic of one or more components of a vehicle and determining one or more expected characteristics for the one or more of the vibration characteristic and the fluid characteristic. The methods may also include determining whether the one or more of the vibration characteristic and the fluid characteristic deviate from the one or more expected respective characteristics, and implementing one or more responsive actions in response to determining that the one or more of the vibration characteristic and the fluid characteristic deviate from the one or more expected characteristics.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Application No. 63 / 152,157, filed February 22, 2021, the entire disclosure of which is incorporated herein by reference. [Background technology]

[0002] The described subject matter relates to a system and method for a control system for early detection of driveline faults in a vehicle.

[0003] Technology Considerations Vehicle systems, such as rail vehicles, are utilized for both the transportation of passengers and / or the transportation of freight. A rail vehicle is typically a vehicle system including multiple vehicles that may be coupled together mechanically, logically, virtually, etc. to travel along a railroad. A vehicle in a vehicle system includes its own set of wheels and optionally corresponding axles. Some vehicles, such as locomotives, include traction motors to provide power to the axles, while other vehicles are simply pushed or pulled along the railroad with the wheels rotating accordingly. Such rail vehicles travel along the multiple tracks of the railroad system, and multiple rail vehicles may utilize the railroad system at any one time.

[0004] When a rail car becomes stuck on the main line of a rail system, it causes excessive delays. As a result, the rail car experiences loss of revenue while simultaneously disrupting traffic on the rail system. It requires a lot of effort and expense to remove a stranded rail car. For example, if a rail car is stopped due to a locked axle, it may be necessary to either replace the locked axle, cut the pinion, or make other temporary fixes on the track. Sometimes when the stoppage occurs in a remote location, it may be difficult to reach the location where facilities to make repairs are not available, causing further difficulties. Summary of the Invention

[0005] In one or more embodiments, a method is provided that may include determining one or more vibration or fluid characteristics of one or more components of a vehicle and determining one or more expected characteristics for the one or more vibration or fluid characteristics. The method may also include determining whether the one or more vibration or fluid characteristics deviate from one or more expected respective characteristics and, in response to determining that the one or more vibration or fluid characteristics deviate from the one or more expected characteristics, performing one or more response actions.

[0006] In one or more embodiments, a method is provided that may include determining one or more of a temperature, a vibration signature, or a fluid lubricant quantity of a first axle of a vehicle and determining one or more of a temperature, a vibration signature, or a fluid lubricant quantity of at least a second axle of the vehicle. The method may also include comparing the one or more of the temperature, vibration signature, or fluid lubricant quantity determined for the first axle to the one or more of the temperature, vibration, or fluid lubricant quantity determined for the at least the second axle, and determining a health of the first axle based on comparing the one or more of the temperature, vibration signature, or fluid lubricant quantity determined for the first axle to the one or more of the temperature, vibration signature, or fluid lubricant quantity determined for the at least the second axle.

[0007] In one or more embodiments, a system is provided that may include one or more sensors that may measure one or more vibration characteristics or fluid lubrication quantities of one or more components of a vehicle. The system may also include one or more processors that may determine one or more expected characteristics for one or more of the vibration characteristics or fluid lubrication quantities. The one or more expected characteristics may be based at least in part on ambient conditions. The one or more processors may determine whether one or more of the vibration characteristics or lubrication characteristics deviate from the one or more expected characteristics. The one or more processors may perform one or more response actions in response to determining that one or more of the vibration characteristics or lubrication characteristics deviate from the one or more expected characteristics.

[0008] In one or more embodiments, a method is provided that may include determining one or more of a vibration characteristic or a fluid lubrication amount of one or more components of a vehicle. The method may also include determining one or more expected characteristics for one or more of the vibration characteristic or the fluid lubrication amount. The one or more expected characteristics may be based at least in part on ambient conditions. The method may also include determining whether one or more of the vibration characteristic or the lubrication characteristic deviate from one or more expected characteristics, and determining a health score for each of a plurality of axles of the vehicle based on the deviation between one or more of the vibration characteristic or the lubrication characteristic and the one or more expected characteristics. The method may also include choosing to stop movement of the vehicle, slow down movement of the vehicle, complete a current run of the vehicle, and prevent further running of the vehicle until the vehicle is repaired, or schedule an inspection of one or more components of the vehicle at a later previously scheduled maintenance of the vehicle. [Brief description of the drawings]

[0009] The subject matter of the present invention can be understood from reading the following description of non-limiting embodiments with reference to the accompanying drawings, in which:

[0010] [Figure 1] 1 illustrates a block schematic diagram of a vehicle system. [Diagram 2] 1 illustrates a block schematic diagram of a control system. [Diagram 3] 1 illustrates a flow block diagram of a method for determining combined probabilities. [Figure 4A] Illustrates a graph of short term oil health. [Figure 4B] 1 illustrates a graph of the probability of a locked axle. [Figure 5A] Illustrates a graph of short term oil health. [Figure 5B] 1 illustrates a graph of the probability of a locked axle. [Figure 6] 1 illustrates a schematic block diagram of the system. [Figure 7] 1 illustrates a flow block diagram of a method for determining a locked axle in a vehicle system. [Figure 8] 1 illustrates a schematic block diagram of the algorithm. [Figure 9] 1 illustrates a schematic block diagram of the algorithm. [Figure 10] 1 illustrates a schematic block diagram of the algorithm. [Figure 11] 1 illustrates a schematic block diagram of the algorithm. [Figure 12] 1 illustrates a schematic block diagram of a Period Algorithm. [Figure 13] 1 illustrates a flow block diagram of a method for determining a potential driveline fault in a vehicle. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Embodiments of the subject matter described herein relate to a system and method for early detection of driveline failures in rail vehicles, where based on the detection and likelihood of failure over a given period of time, action is taken to reduce the probability or prevent driveline failure. By making a determination and taking action to mitigate the driveline failure, the disruption caused by a stranded vehicle system is reduced.

[0012] 1 illustrates a schematic diagram of an example vehicle system 100 including a control system 102. The vehicle system may travel along a path 104 in a progression from a start or departure location to a destination or arrival location. The vehicle system includes at least one propulsion-powered vehicle 108 and, optionally, at least one non-propulsion-powered vehicle 110 that are mechanically interconnected to each other for traveling together along the path. Alternatively, the vehicle system may be formed of only a single propulsion-powered vehicle or only two or more propulsion-powered vehicles.

[0013] A propulsion-powered vehicle may generate traction forces to propel (e.g., pull or push) the vehicle system along a path. A propulsion-powered vehicle includes a propulsion subsystem, e.g., an engine, one or more traction motors, and / or the like, that operates to generate traction forces to propel the vehicle system. A propulsion-powered vehicle also includes a braking system that generates braking forces to slow or stop the movement of the vehicle system. Although one propulsion-powered vehicle and one non-propulsion-powered vehicle are shown in FIG. 1, a vehicle system may include multiple propulsion-powered vehicles and / or multiple non-propulsion-powered vehicles. In yet another embodiment, the vehicles in a vehicle system are logically or virtually coupled together but are not mechanically coupled together.

[0014] In the example of FIG. 1, the vehicles of the vehicle system each include a number of path-engaging wheels 120 and at least one axle 122 coupling left and right wheels together (only the left wheels are shown in FIG. 1). Optionally, the wheels and axles are located on one or more freight cars or dollies 118. Optionally, the freight cars may be fixed-axle freight cars, such that the wheels are rotationally fixed to the axles, so that the left wheels rotate at the same speed, amount, and time as the right wheels. In an embodiment, the vehicle system may not include axles, such as some mining vehicles, electric vehicles, etc.

[0015] The control system may further include a wireless communication system 126 that enables wireless communication between vehicles in the vehicle system and / or with remote locations, such as a remote (e.g., dispatch) location 128. The communication system may include a receiver and a transmitter, or a transceiver that performs both receiving and transmitting functions. The communication system may also include an antenna and associated circuitry.

[0016] The control system further includes a controller 129 that includes a driving characterization element 130, which in one example may include characterization circuitry in communication with one or more processors. The driving characterization element may provide information regarding the vehicle system's driving along a route. The driving information may include route characteristics, designated locations, designated stopping locations, schedule times, passing events, direction along the route, etc.

[0017] In an embodiment, the controller may also include a vehicle characterization element 134. The vehicle characterization element may provide information regarding the configuration of the vehicle system, such as the type of non-propulsion-powered vehicles (e.g., manufacturer, part number, material, etc.), the number of non-propulsion-powered vehicles, the weight of the non-propulsion-powered vehicles, whether the non-propulsion-powered vehicles are consistent (meaning relatively the same weight and distribution over the length of the vehicle system) or inconsistent, the type and weight of cargo, the total weight of the vehicle system, the number of propulsion-powered vehicles, the location and arrangement of the propulsion-powered vehicles relative to the non-propulsion-powered vehicles, the type of propulsion-powered vehicles (including manufacturer, part number, power capabilities, available notch settings, fuel usage, etc.).

[0018] The vehicle characterization elements may be electronic storage devices, or databases stored in memory. Information in the vehicle characterization elements may be entered by an operator using input / output (I / O) devices (referred to as user interface devices), may be automatically uploaded, or may be received remotely via a communication system. The source of at least some of the information in the vehicle characterization elements may be a vehicle manifest, a log, or the like.

[0019] FIG. 2 provides a schematic illustration of a controller 200 that may control the operation of a propulsion-powered vehicle. In one example, the controller represents the controller of FIG. 1. The controller may be a device that includes one or more processors 202 (microprocessors, integrated circuits, field programmable gate arrays, etc.). The controller may also optionally include a controller memory 204, which may be an electronic computer-readable storage device or medium. The controller memory may be within the housing of the controller, or alternatively, on a separate device that may be communicatively coupled to the controller and one or more processors therein. "Communicatively coupled" means that two devices, systems, subsystems, assemblies, modules, components, etc. are coupled by one or more wired or wireless communication links, such as one or more electrically conductive (e.g., copper) wires, cables, or buses, wireless networks, fiber optic cables, etc. The controller memory may include a tangible, non-transitory computer-readable storage medium that temporarily or permanently stores data for use by one or more processors. The memory may include one or more volatile and / or non-volatile memory devices, such as random access memory (RAM), static random access memory (SRAM), dynamic RAM (DRAM), another type of RAM, read only memory (ROM), flash memory, magnetic storage (e.g., hard disk, floppy disk, or magnetic tape), optical disk, etc. The memory may be utilized to store information related to vehicle parameters, route characteristics, driving parameters, etc. Vehicle parameters may include vehicle weight, wheel diameter, tachometer reading, throttle setting, brake setting, speed, brake setting, acceleration, etc. Route characteristics may include route gradient, route weather, route curvature, etc. Driving parameters may include destination, area speed limit, traffic congestion, rest areas, tunnel locations, etc.

[0020] The controller may also include a transceiver 206 that may communicate with a remote device 208. The transceiver may be a single unit or may be a separate receiver and transmitter. In one example, the transceiver may only transmit signals. The remote device 208 may be a dispatch controller, a controller in another vehicle, a second controller coupled to the vehicle system, a controller in a roadside unit, etc.

[0021] The controller may also include or communicate with one or more sensors 210 coupled to the vehicle system to detect vehicle parameters, route characteristics, driving parameters, and the like. In one embodiment, the at least one sensor is a temperature sensor that measures the temperature of a component of the vehicle system. For example, the temperature sensor may be an axle bearing temperature sensor that may measure either the pinion end (PE) bearing or other bearings, an oil temperature sensor that measures the temperature of oil utilized in association with the axle and axle bearings, or an oil temperature sensor that may or may not be utilized in association with an ambient temperature sensor, an engine temperature sensor, a motor winding temperature sensor, and the like. In another embodiment, the at least one sensor may be a vibration sensor associated with a component of the vehicle system. For example, the vibration sensor may be a bearing vibration sensor, a gear vibration sensor, a gear case vibration sensor, a gear sound sensor, a vibration sensor that detects wheel acceleration caused by a flat spot, and the like. In particular, the vibration sensor may detect the amplitude, frequency, amplitude, and the like of a particular frequency range of interest. Alternatively, the at least one sensor may be an oil fluid level sensor for the engine or gear case, a sensor that detects ambient conditions of the vehicle system or a component of the vehicle system, a vehicle motion sensor including a speed sensor, and the like. Combinations of each of these sensors may also be provided. Specifically, each sensor may detect or monitor operation to obtain data that may be utilized for early detection of driveline failure. In one example, a determination is made as to whether a locked axle is more or less likely to occur for a particular axle.

[0022] The controller may also include input devices 212 and output devices 214. Specifically, the input devices may be an interface between an operator and one or more processors. The input devices may include a display or touch screen, input buttons, a port for accepting a memory device, and the like. In this manner, the operator may manually provide parameters to the controller, including vehicle parameters, route characteristics, trip parameters, and the like. Similarly, the output devices may present information and data to the operator, or provide prompts for information and data. The output devices may likewise be a display or touch screen. In this manner, the display or touch screen may be an input device and an output device. The controller may also receive inputs from both the vehicle characterization element 218 and the trip characterization element 220.

[0023] FIG. 3 illustrates a method 300 for determining a combined probability that a locked axle will occur over a determined time period. In the example of FIG. 3, a locked axle is determined, although in other exemplary embodiments, other conditions may be determined. The methodology of FIG. 3 may be used as the basis for the methodology of FIG. 7, which may determine a health score and take active action to prevent a vehicle system shutdown as a result of the conditions determined in FIG. 3. Specifically, by utilizing the strategies and methodologies of FIG. 3, a health score may ultimately be determined for each axle in a vehicle system based on the difference between expected vehicle characteristics compared to measured vehicle characteristics.

[0024] In step 302, a first characteristic is monitored. The first characteristic may be a vibration characteristic, a fluid characteristic, a temperature characteristic, a lubricant contaminant characteristic, and the like. The first characteristic may be monitored by one or more sensors. In an exemplary embodiment, the one or more sensors may include a thermometer, an acoustic sensor, an optical sensor, an infrared sensor, a vibration sensor, an accelerometer, a gear case sensor, an axle bearing temperature sensor, an oil temperature sensor, a motor winding temperature sensor, and the like. By monitoring the first characteristic with the sensor, readings, data, information, and the like related to the first characteristic are obtained. In one example, the vibration characteristic is a vibration signature from a vibration sensor, the fluid characteristic is a fluid lubricant contaminant amount, and the temperature characteristic is a temperature.

[0025] In step 304, a first probability that a locked axle will occur in a given time period is determined. The given time period may be a duration, such as three days. In another example, the time period is related to a number of miles (or kilometers). Specifically, by monitoring the first characteristic, a probability may be determined as to when a locked axle will occur.

[0026] In one exemplary embodiment, the oil level in the gear case is the fluid characteristic monitored. FIG. 4A is a graph illustrating short term oil health 402 as a function of oil level 404. Specifically, as the percentage of oil decreases, the oil health condition also decreases. In this manner, a first probability based on the first characteristic may be determined. FIG. 4B illustrates a first probability of an axle being locked based on oil level 406 within a determined time period, such as one week, based on the short term oil health condition. Similarly, the first probability may be a determined distance traveled, such as within 100 miles. As illustrated by the graph, as the oil health decreases, the first probability of an axle being locked increases.

[0027] In step 306, the second characteristic is monitored. The second characteristic may be a vibration characteristic, a fluid characteristic, a temperature characteristic, a lubricant contaminant characteristic, and the like. The characteristic may be monitored by one or more sensors. In an exemplary embodiment, the one or more sensors may include a thermometer, an acoustic sensor, an optical sensor, an infrared sensor, a vibration sensor, an accelerometer, a gear case sensor, an axle bearing temperature sensor, an oil temperature sensor, a motor winding temperature sensor, and the like. By monitoring the second characteristic with the sensor, readings, data, information, and the like related to the second characteristic are obtained. In one example, the vibration characteristic is a vibration signature from a vibration sensor, the fluid characteristic is a fluid lubricant quantity, and the temperature characteristic is a temperature.

[0028] In step 308, a second probability that a locked axle will occur in a given time period is determined. The given time period can be a duration, such as 3 days. In another example, the time period is related to a number of miles (or kilometers). Specifically, by monitoring the second characteristic, a second probability as to when a locked axle will occur can be determined. FIG. 5A illustrates a graph of short-term oil health 408 as a function of oil temperature 410. As the temperature of the oil in the gear case increases, the short-term oil health decreases. FIG. 5B illustrates a second probability of a locked axle based on oil temperature 412 within a determined time period, such as one week, based on the short-term oil health status. Similarly, the second probability can be a determined distance traveled, such as within 100 miles. As illustrated by the graph, as the oil temperature increases, the second probability of a locked axle increases as well.

[0029] In step 310, the first probability and the second probability are combined to form a combined probability that a locked axle will occur in a given time period. Additionally, additional probabilities may be included to determine the combined probability that a locked axle will occur in a given time period. FIG. 6 illustrates a schematic block diagram of a system 600 for determining the probability of a locked axle. In this example, inputs 602A, 602B, 602C, and 602D are provided as a result of monitoring for the characteristic. From the monitored inputs, a first probability 604A, a second probability 604B, a third probability 604C, and a fourth probability 604D are all determined based on the individual inputs. In one example, the first probability 604A is a probability of a locked axle based on oil level. In one embodiment, the probability of a locked axle based on oil level is determined as provided by the graphs of FIG. 4A and FIG. 4B. In another embodiment, the second probability is a probability of a locked axle based on oil temperature. In one example, the probability of a locked axle based on oil temperature is determined as provided by graphs FIG. 5A and FIG. 5B. In another example, a third probability is a probability of a locked axle based on gear case vibration and a fourth probability is a probability of a locked axle based on wheel defects. The first, second, third, and fourth probabilities are then utilized to determine a combined probability of a locked axle for a period of time. The combined probability of a locked axle may be determined by averaging the probabilities, giving more or less weight to certain probabilities, selecting the highest probability, etc. By utilizing a combination of variables, accuracy may be improved and locked axles may be prevented through maintenance and other preventative measures.

[0030] 7 illustrates a method 700 for determining the likelihood of a rail vehicle driveline failure for a vehicle system as a result of a locked axle. In one example, the vehicle system is the vehicle system of FIG. 1. In another example, the method is performed by the controller of FIG. 2. In one embodiment, the vehicle system is a rail vehicle system. In other embodiments, the vehicle system is one of an off-road vehicle(s), a trolley(s), a fleet of aircraft, a fleet of ships, etc.

[0031] In step 702, one or more of vibration characteristics, fluid characteristics, or temperature characteristics of one or more components of the vehicle are determined. In an example, the determination may be performed by a controller. In an example, the vehicle is part of a vehicle system. The vibration characteristics may be any readings, data, information, signals, currents, slips, amplitudes, frequencies, vibration amplitudes, etc. of a particular frequency range of interest that are related to or associated with vibration. The readings, data, information, signals, currents, slips, amplitudes, frequencies, vibration amplitudes, etc. of a particular frequency range of interest may be related to or associated with vibration if it provides vibration of any component of the vehicle or can be utilized to obtain vibration of any component of the vehicle. The vibration characteristics may be provided by readings, data, information, signals, currents, slips, capacitances, amplitudes, frequencies, vibration amplitudes, etc. of a particular frequency range of interest. The vibration characteristics may be obtained utilizing an algorithm, a mathematical equation, a mathematical model, a function, a lookup table, a decision tree, etc. The determined vibration characteristics may include one or more of bearing vibrations of one or more bearings of an axle of the vehicle, gear vibrations of one or more gears of the vehicle, gear borne vibrations generated by one or more gears of the vehicle, air borne vibrations, structure borne vibrations, case vibrations of a gear case of the vehicle, acceleration of one or more wheels of the vehicle, vibration signatures, etc.

[0032] The temperature characteristic may be any reading, data, information, signal, current, slip, capacitance, etc. that is related or associated with temperature. The reading, data, information, signal, current, slip, capacitance, etc. may be related or associated with temperature if it provides the temperature of any component of the vehicle. The temperature characteristic may be obtained utilizing an algorithm, a mathematical equation, a mathematical model, a function, a lookup table, a decision tree, etc. The determined temperature characteristic may include one or more of temperature, fluid temperature, lubricant temperature, axle bearing temperature (including bearing elements, raceways, tubes, etc.), including PE bearing temperature and CE bearing temperature, motor winding temperature, etc.

[0033] In an exemplary embodiment, the characteristic may be two or more of a vibration characteristic, a fluid characteristic, and a temperature characteristic. For example, the temperature of a fluid, such as oil in a gear case, may be both a fluid characteristic and a temperature characteristic.

[0034] Similarly, a fluid characteristic may be any reading, data, information, signal, current, slip, capacitance, etc., related to or associated with a fluid. A reading, data, information, signal, current, slip, capacitance, etc. may be related to or associated with a fluid if it provides a characteristic of the fluid of the vehicle or may be utilized to obtain a characteristic of the fluid of the vehicle. A fluid characteristic may be provided by a reading, data, information, signal, current, slip, capacitance, etc. A fluid characteristic may be obtained utilizing an algorithm, a mathematical equation, a mathematical model, a function, a lookup table, a decision tree, etc. The determined fluid characteristic may include one or more of a fluid volume, an axle bearing temperature of one or more bearings of an axle of the vehicle, a motor bearing temperature of one or more traction motor bearings, a combined bearing temperature of one or more combined bearings, a journal bearing temperature of one or more journal bearings, a fluid temperature of one or more lubricants of a gear case or engine of the vehicle, a motor winding temperature of one or more conductive windings of a motor of the vehicle, a lubricant or fluid level, etc.

[0035] At step 704, one or more predicted properties are determined for one or more of the vibration, fluid, or temperature properties. A predicted property is a property that is calculated or determined, as opposed to an actual property that may be directly measured or determined based on direct measurement. Specifically, a calculation or determination may be made for each vibration, fluid, and temperature property in the absence of component failures based on forces acting on the vehicle, vehicle components, etc. For example, a calculation may be made for a predicted lubricating fluid temperature for an axle gear case if the rail vehicle travels 100 miles with an average vehicle speed of 50 mph and an average axle power of 500 HP.

[0036] On the other hand, actual fluid temperature may also be determined directly by a sensor immersed in the oil. In this manner, fluid temperature calculated from variables such as distance traveled, vehicle speed, etc. is an expected fluid property, and fluid properties measured directly by a temperature sensor are not expected fluid properties. Specifically, in one example, a vehicle includes multiple axles, and one or more of vibration properties, fluid properties such as lubricant level, or temperature properties are determined for a first axle of the axles, and one or more expected vibration properties, fluid properties, or temperature properties are determined based at least in part on the operation of a set of axles that does not include the first axle. Specifically, the expected vibration properties and fluid properties need not utilize direct measurements of the axles.

[0037] In one example, the expected characteristics may be determined utilizing information from a remote location. In particular, in a rail vehicle embodiment, a positive vehicle controller (PVC) may be utilized to limit and control the movement of the rail vehicle on the rail system with respect to other rail vehicles utilizing the rail system. Such information, which is continuously acquired, may be utilized to make determinations and calculations related to the expected characteristics. Additionally, a controller with trip optimizer software may be utilized that continuously acquires data, information, etc., related to the rail vehicle. Specifically, the trip optimizer software functions to achieve goals associated with any individual trip. For example, it may be desired that a particular trip be performed within a certain amount of time and with a certain amount of pollution generated. The trip optimizer software then operates the rail vehicle to operate in a manner that meets these objectives. Yet, to achieve such optimization, information, data, etc. is continuously collected. Such information, data, etc. may be utilized to make determinations and calculations related to the expected characteristics.

[0038] In an exemplary embodiment, one or more expected characteristics may be based at least in part on ambient conditions. Such ambient conditions may be utilized in combination with a direct measurement related to the expected characteristic or without utilizing a direct measurement of the expected characteristic. The ambient conditions may include one or more of the following: rotational speed of one or more wheels of the vehicle, ambient temperature, ambient sound, a route characteristic of a route on which the vehicle is traveling, a vehicle characteristic of the vehicle, an accelerator torque applied to one or more axles of the vehicle, a route or railroad soundness or irregularity, the presence of one or more gaps in the route, a curvature of the route, a position of the vehicle on the route, or an inconsistency in the route as a route characteristic, a vehicle weight, a vehicle speed, a size of the wheels of the vehicle, an estimated dynamic axle weight as a vehicle characteristic, and the like.

[0039] In another example, the one or more expected characteristics for one or more of the vibration characteristics, hydrodynamic lubrication, or thermal lubrication may also be based on vehicle operation. In particular, the one or more expected characteristics may be based on vehicle operation including one or more of vehicle speed, axle torque exerted on an axle of the vehicle, ambient temperature, one or more characteristics of a path the vehicle is traveling, one or more characteristics of the vehicle, etc.

[0040] In step 706, one or more of the vibration characteristic, the fluid characteristic, or the temperature characteristic are determined to have deviated from one or more expected respective characteristics. In one example, the vibration characteristic, the fluid characteristic, or the temperature characteristic may be compared to the expected respective characteristics. In another example, a mathematical function, a mathematical model, a look-up table, a decision tree, a function, an algorithm, or the like may be utilized to determine the deviation. In another example, a tolerance may be determined such that if the difference between the vibration characteristic, the fluid characteristic, or the temperature characteristic is not greater than the tolerance, a deviation determination is not provided. In another embodiment, the tolerance may be based on the determined amount. For example, if the fluid characteristic is an oil temperature of an oil lubricating a bearing in a bearing assembly, the determined tolerance may be 5 degrees Fahrenheit (or about 2 degrees Celsius). In this manner, if the fluid characteristic of the oil is 300 degrees Fahrenheit (150 degrees Celsius) when the expected fluid characteristic of the oil is 297 degrees Fahrenheit (149 degrees Celsius), the fluid characteristic is determined not to have deviated from the expected respective oil temperature. If the expected fluid characteristic of the oil is 290 degrees Fahrenheit (143 degrees Celsius), then the fluid characteristic deviates from the expected fluid characteristic. In other embodiments, a percentage difference may be utilized instead of a determined amount. In this manner, as the vibration characteristic, fluid characteristic, or temperature characteristic increases or decreases, the tolerance range may increase or decrease as well. In yet another example, the fluid characteristic may indicate the amount of lubricant contaminants. Such contaminants may include water, soot, dirt, metal particles, and the like. Such characteristics may indicate the need for fluid replacement and / or seal or gasket repair. Thus, an amount of contaminants that is outside of a determined range may indicate such a need.

[0041] If a determination is made at step 706 that a deviation between the vibration, fluid, or temperature characteristics has not occurred, the vibration, fluid, or temperature characteristics continue to be determined at 704. If a determination is made that a deviation between the vibration, fluid, or temperature characteristics has occurred, a health score for each of a plurality of axles of the vehicle is determined at 708 based on the deviation between one or more of the vibration, lubrication, or temperature characteristics and one or more expected characteristics. In one example, the method of FIG. 3 is utilized to determine the scored health. In particular, a determination may be made regarding the health of the axles.

[0042] Vibration, fluid, and temperature characteristics can be utilized to determine the health of an axle and the probability that a driveline failure may occur. For example, if a gear case is provided with a reduced oil level, an increased probability of a locked axle may be provided. If the oil temperature in the gear case increases, the probability of a locked axle may increase. If the gear case vibration increases, an increased probability of a locked axle may be provided. If the axle bearing temperature or bearing race temperature increases, an increased probability of a locked axle may be provided. Gear or wheel defects may also increase the probability of a locked axle. In yet another example, motor winding temperature may be an indication of an increased probability of a locked axle.

[0043] In many of the cases and examples provided, it is expected that temperature or vibration will increase during operation, based on the forces acting on the vehicle system, in addition to historical information related to such characteristics, and an increase in above expected is an indication that the probability of a locked axle has increased. Thus, by monitoring one of these characteristics, a probability associated with the possibility of a locked axle can be determined. In some embodiments, more than one probability may be utilized to determine an overall probability of a locked axle. For example, both gear case temperature and gear case fluid level may be monitored and the probability of a locked axle determined relative to both. In one example, the probabilities may be averaged to determine an overall probability of a locked axle. In another embodiment, the determined probability may be weighted based on the determined factors, the severity of the deviation from the expected value, etc. In yet another embodiment, an algorithm may be utilized to make such a probability determination. Overall, based on the vibration, fluid, and / or temperature characteristics, the health of the axle may be determined based on the determined probabilities. Based on the probabilities, a heath score may be provided. The health score may be determined by a lookup table, a decision tree, an algorithm, a mathematical function, a mathematical model, or the like.

[0044] In step 710, a response action may be implemented based on the health score. Specifically, if the health score indicates that there is a high probability of a locked axle occurring, different response actions may occur based on the health score. The response actions may include sending an alert to the driver, sending an alert to an off-vehicle system including a PVC device or a depot device, sending an alert to another vehicle or vehicle system, generating a notification to an off-vehicle facility to determine if a repair of the vehicle or a change in the scheduled dispatch of the vehicle should occur, communicating vibration characteristics, fluid characteristics, or temperature characteristics to an off-vehicle system, modifying the axle torque applied to one or more of the axles to de-power at least one of the axles and increase the axle torque applied to one or more others of the axles, stopping movement of the vehicle, slowing movement of the vehicle, preventing further travel of the vehicle until repair, scheduling inspection of one or more components, etc. The alert may include a visual message, an audible message, an audible sound, a flashing light, etc. The notification may include an electronic message (email), a text message, an automated voice message, etc. Specifically, based on the health score, response actions may be taken to prevent a locked axle before it occurs.

[0045] Figure 8 is an illustrative example algorithm 800 utilized for implementing the method of Figure 7. In this example, a health score is determined based on characteristics associated with a vehicle system related to the health of an axle bearing. More specifically, the determination is based on the operation of the vehicle system.

[0046] The first characteristic 802, the second characteristic 804, the third characteristic 806, the fourth characteristic 808, and the fifth characteristic 810 are utilized in making a determination 812 of an expected temperature of the bearing. The bearing may be a PE bearing, a CE bearing, or the like. In one example, the first characteristic is an axle rotational speed, the second characteristic is an axle torque, the third characteristic is an ambient temperature of the bearing's surrounding environment, the fourth characteristic is a track characteristic such as grade, curvature, and the fifth characteristic is a vehicle characteristic such as material of the bearing elements, axle size, and the like. Each of the characteristics may be utilized to determine an expected temperature of the bearing, and thus is a temperature characteristic. Specifically, each may be utilized to calculate friction and other temperature based characteristics. The characteristics 802-810 may be received from sensors, vehicle characterization elements, trip characterization elements, off-board equipment, trip plans, off-board PTC controllers, and the like. The determination of the expected temperature may be based on mathematical calculations, models, functions, and the like.

[0047] After determining the predicted temperature, the predicted temperature 814 and the measured temperature 816 are both provided to a health determination algorithm 818. The health determination algorithm utilizes both the predicted temperature and the measured temperature to make a determination related to bearing degradation 820 as a result of operation. In this example, a tolerance 822 is provided for typical variations between such measurements. A bearing health score 824 is then provided based on the predicted temperature compared to the measured temperature. Depending on the health score, response actions may be taken including providing an alert, notifying the driver or a third party, scheduling a maintenance appointment, reducing the axle torque of the bearing, shutting down the vehicle system, reducing the vehicle speed of the vehicle system, etc. In this manner, the bearing health score is utilized to mitigate risks associated with locked axles.

[0048] FIG. 9 illustrates yet another exemplary algorithm 900 utilized for implementation of the method of FIG. 7. In this example, an axle health score is determined based on a comparison with another axle. Specifically, each axle of a vehicle system needs to provide relatively the same characteristics as the other axles. As a result, if one axle behaves or performs significantly worse than another axle, an indication of the possibility of the axle being locked is provided. Furthermore, if sensors are coupled to the axles, a vibration signal common to multiple axles may indicate poor track surface conditions. This information can be used to drive infrastructure work ranges or operating speed limits.

[0049] In determining the health of each axle, in the exemplary algorithm of FIG. 9, a first characteristic 902 and a second characteristic 904 are associated with a first axle, and a third characteristic 906 and a fourth characteristic 908 are associated with another axle, or a second axle. Each of the characteristics is input to a determination 910 of an expected temperature of the bearing. The bearing may be a PE bearing, a CE bearing, etc. For example, the first characteristic may be a bearing temperature of the first axle, and the second characteristic may be a duty characteristic, such as an axle torque requirement, of the first axle. The third characteristic may be a bearing temperature of the second axle, and the fourth characteristic may be an axle torque requirement of the second axle. Based on these inputs, a determination may be made related to the expected temperature.

[0050] Similar to the embodiment of FIG. 8, after the determination of the predicted temperature, both the predicted temperature 914 and the measured temperature 916 are provided to a health determination algorithm 918. The health determination algorithm utilizes both the predicted temperature and the measured temperature to make a determination related to bearing degradation 920 as a result of operation. In this example, a tolerance 922 is provided for typical variations between such measurements. A bearing health score 924 is then provided based on the predicted temperature compared to the measured temperature. Depending on the health score, response actions may be taken including providing an alert, notifying the driver or a third party, scheduling a maintenance appointment, reducing torque on axles with bearings having poor health scores, shutting down the vehicle system, reducing vehicle speed of the vehicle system, etc.

[0051] Figure 10 illustrates yet another example algorithm 1000 utilized for implementation of the method of Figure 7. In this example, an axle health score is determined based on sensors in the driveline. In particular, expected temperatures may be determined by utilizing vibration, fluid, and / or temperature characteristics associated with the driveline.

[0052] In the exemplary algorithm of FIG. 10, a first characteristic 1002 may be related to a bearing structure, such as an axle bearing temperature, while a second characteristic 1004 and a third characteristic 1006 may be related to the driveline. In one example, the second characteristic is engine oil temperature and the third characteristic is motor temperature. Each of the characteristics is input to a determination 1010 of an expected temperature of the bearing. The bearing may be a PE bearing, a CE bearing, etc. As with the embodiment of FIGS. 8-9, the determination of the expected temperature may be made utilizing a mathematical function, a mathematical model, a computer generated model, a lookup table, a decision tree, etc. In yet another example, additional driveline characteristics may be utilized. In such an embodiment, the three driveline related characteristics may be compared to determine if one of the measured characteristics provides a fault to the measurements. Thus, by utilizing a comparison, one or more response actions implemented may be limited based on the comparison to eliminate false positives of vehicle faults.

[0053] Similar to the embodiment of FIGS. 8-9, after the determination of the predicted temperature, both the predicted temperature 1014 and the measured temperature 1016 are provided to a health determination algorithm 1018. The health determination algorithm utilizes both the predicted temperature and the measured temperature to make a determination related to bearing degradation 1020 as a result of operation. In this example, a tolerance 1022 is provided for typical variations between such measurements. A bearing health score 1024 is then provided based on the predicted temperature compared to the measured temperature. Depending on the health score, response actions may be taken including providing an alert, notifying the driver or a third party, scheduling a maintenance appointment, reducing torque on axles with bearings having poor health scores, shutting down vehicle systems, reducing vehicle system power or vehicle speed, etc.

[0054] Figure 11 illustrates yet another example algorithm 1100 utilized for implementation of the method of Figure 7. In this example, the axle health score is determined based on a comparison of delta temperature versus expected delta. In particular, the expected temperature may be determined by utilizing vibration characteristics, fluid characteristics, and / or temperature characteristics associated with the driveline.

[0055] In the exemplary algorithm of FIG. 11, a first characteristic 1102 may relate to a temperature of a PE bearing, and a second characteristic 1104 may relate to a temperature of a CE bearing. Each of the characteristics is input to a determination 1010 of an expected temperature of the bearing. The bearing in this exemplary embodiment is a PE bearing. As with the embodiments of FIGS. 8-10, the determination of the expected temperature may be made utilizing a mathematical function, a mathematical model, a computer generated model, a look-up table, a decision tree, or the like.

[0056] Similar to the embodiment of FIGS. 8-10, after the determination of the predicted temperature, both the predicted temperature 1114 and the measured temperature 1116 are provided to a health determination algorithm 1118. The health determination algorithm utilizes both the predicted temperature and the measured temperature to make a determination related to bearing degradation 1120 as a result of operation. In this example, a tolerance 1122 is provided for typical variations between such measurements. A bearing health score 1124 is then provided based on the predicted temperature compared to the measured temperature. Depending on the health score, response actions may be taken including providing an alert, notifying the driver or a third party, scheduling a maintenance appointment, reducing torque on axles with bearings having poor health scores, shutting down the vehicle system, reducing vehicle speed of the vehicle system, etc.

[0057] 8-11 all demonstrate an exemplary embodiment in which a predicted temperature of an axle bearing is determined and compared to a measured temperature of the axle bearing to determine an axle bearing health score. Additionally, utilizing a similar methodology, health scores of other characteristics may be determined and utilized to determine an axle health score, and then action may be taken to mitigate a potential locked axle.

[0058] FIG. 12 illustrates a de-powering algorithm 1200 provided for mitigation of a potential locked axle. As illustrated, first, second, third, fourth, fifth, and sixth health scores 1202A-F are illustrated. In this embodiment, six health scores are utilized, although in other embodiments, only one health score may be utilized. Alternatively, more than six health scores are utilized. Specifically, more than one health score may be utilized, with more health scores utilized providing more accurate results. For the embodiment of FIG. 12, in one example, the first health score is a lubricant level for a gear case health score, the second health score is a lubricant temperature for a gear case health score, the third health score is a vibration for a gear case health score, the fourth health score is a gear health score, the fifth health score is a PE temperature health score, and the sixth health score is a wheel defect health score. In an exemplary embodiment, the PE temperature health score is determined utilizing the algorithms of FIGS. 8-11. As shown, by using vibration, fluid, and / or temperature characteristics, multiple health scores can be determined to improve the accuracy of determining the health of the axle.

[0059] For each health score, a weighting 1204A-F is provided. The weighting may be determined based on the health score. In one example, the worse the health score, the more weighting is provided for that health score. In this way, if the wheel defect score is such that a locked axle is expected in the next 50 miles of travel, and all other scores indicate that a locked axle is not expected until another 10,000 hours or more have passed, then significantly more weighting is provided for the wheel defect score so that accurate results are presented.

[0060] Alternatively, the weighting may depend on the accuracy of the health score. In one embodiment, the health score is on a scale of 1 to 100. In an example of such an embodiment, when the health score based on lubricant temperature falls below 20, there is a 95% chance of the axle locking during the next 100 miles of driving, whereas when the health score based on bearing vibration falls below 20, there is only a 50% chance of the axle locking. Specifically, in such an embodiment, the type of vibration sensor measuring the bearings may not be as accurate as the lubricant temperature system. As a result, more weighting is provided to a health score based on a lubricant temperature below 20 than to a health score based on bearing vibration below 20. Alternatively, in other examples, the weighting may be calculated utilizing a mathematical model, function, lookup table, decision tree, or the like.

[0061] Based on the weights, a maximum score 1206A-F is provided. The maximum score may be determined in any of the methods for making the determination discussed above. A minimum score 1208 for each axle may then be determined based on the maximum score, and an axle health score 1210A-C for each axle may be provided. From the axle health scores 1210A-C for each axle, a response action 1212 may be taken to prevent a locked axle from occurring during a run. For example, based on the axle health score for each axle, a minimum time period until predicted failure, or a high probability of failure, may be provided. A high probability of failure may include a greater than 50% probability that a locked axle will occur during the run. Alternatively, a high probability of failure may include a greater than 20% probability that a locked axle will occur during the minimum time period. The minimum time period may be provided in terms of time, distance, etc. In one example, the minimum time period may be 10 runs of more than 3 hours, 500 miles, 300 miles, etc. at the current vehicle speed.

[0062] In this manner, information is provided that may be utilized in taking responsive actions to prevent a locked axle from occurring during travel. Such responsive actions may include derating the identified axle to decrease the axle torque of the identified axle while increasing the axle torque of healthier axles, decreasing the vehicle speed of the vehicle system, preventing the vehicle system from leaving a station or depot after a stop until repairs occur, scheduling repairs, skipping pre-planned stops in favor of previously unscheduled stops when maintenance may occur, reporting the axle health score to a third party device, changing the driver of the axle health score, etc.

[0063] 13 illustrates an exemplary embodiment of a flow block diagram of a method 1300 for detection of a driveline fault in a rail vehicle. In one example, the vehicle system is the vehicle system of FIG. 1. In another example, the method is performed by the controller of FIG. 2. In one embodiment, the vehicle system is a rail vehicle system. In other embodiments, the vehicle system is one of an off-road vehicle(s), a trolley(s), a fleet of aircraft, a fleet of ships, etc.

[0064] In step 1302, one or more of vibration characteristics, fluid characteristics, or temperature characteristics of one or more components of the vehicle are obtained. In an example, the characteristics may be obtained by a sensor, an in-vehicle controller, a trip plan, or the like. In an example, the vehicle is part of a vehicle system. The vibration characteristics may be any reading, data, information, signal, current, slip, capacitance, or the like that is related to or associated with vibration. A reading, data, information, signal, current, slip, capacitance, or the like may be related to or associated with vibration if it provides a vibration of any component of the vehicle or may be utilized to obtain a vibration of any component of the vehicle. The vibration characteristics may be provided by a reading, data, information, signal, current, slip, capacitance, or the like. The vibration characteristics may be obtained utilizing an algorithm, a mathematical equation, a mathematical model, a function, a lookup table, a decision tree, or the like. In an example, the vibration characteristics is a vibration signature.

[0065] The temperature characteristic may be any reading, data, information, signal, current, slip, capacitance, etc. that is related or associated with temperature. A reading, data, information, signal, current, slip, capacitance, etc. may be related or associated with temperature if it provides the temperature of any component of the vehicle. The temperature characteristic may be obtained utilizing an algorithm, a mathematical equation, a mathematical model, a function, a lookup table, a decision tree, etc. In one example, the temperature characteristic is temperature.

[0066] Similarly, a fluid characteristic may be any reading, data, information, signal, current, slip, capacitance, etc., related to or associated with a fluid. A reading, data, information, signal, current, slip, capacitance, etc. may be related to or associated with a fluid if it provides a characteristic of the vehicle's fluid or may be utilized to obtain a characteristic of the vehicle's fluid. A fluid characteristic may be provided by a reading, data, information, signal, current, slip, capacitance, etc. A fluid characteristic may be obtained utilizing an algorithm, a mathematical equation, a mathematical model, a function, a lookup table, a decision tree, etc. In one example, a fluid characteristic may be a fluid volume.

[0067] In step 1304, the vibration characteristic, fluid characteristic, or temperature characteristic is communicated to an off-vehicle system. The off-vehicle system may be a PTC, a station controller, a maintenance controller, a client controller, a customer controller, etc. The off-vehicle system may include additional historical information and data related to the vehicle system, the route of the vehicle system, the route characteristics, other similar vehicle systems, other similar vehicle systems that have previously traveled the route, etc. Based on the characteristics, the vibration characteristic, fluid characteristic, or temperature characteristic may be determined by the off-vehicle system. The determined vibration characteristic may include one or more of bearing vibration of one or more bearings of an axle of the vehicle, gear vibration of one or more gears of the vehicle, gear transmitted vibration generated by one or more gears of the vehicle, air transmitted vibration, structure transmitted vibration, case vibration of a gear case of the vehicle, acceleration of one or more wheels of the vehicle, etc. The determined temperature characteristic may include one or more of fluid temperature, lubricant temperature, axle bearing temperature including PE bearing temperature and CE bearing temperature (including temperatures of bearing elements, raceways, tubes, etc.), winding temperature, etc. In an exemplary embodiment, the characteristic may be two or more of a vibration characteristic, a fluid characteristic, and a temperature characteristic. For example, the temperature of a fluid, such as oil, in a gear case may be both a fluid characteristic and a temperature characteristic. The determined fluid characteristic may include one or more of an axle bearing temperature of one or more bearings of an axle of the vehicle, a motor bearing temperature of one or more traction motor bearings, a combined axle bearing temperature of one or more combined bearings, a journal bearing temperature of one or more journal bearings, a fluid temperature of one or more lubricants of a gear case or engine of the vehicle, a winding temperature of one or more conductive windings of a motor in the vehicle, a lubricant or fluid level, etc.

[0068] In step 1306, the vibration, fluid, or temperature characteristics are determined by comparing the characteristics of the vehicle to similar characteristics measured for another vehicle. In an example, where the vibration characteristics include axle size, vehicle size, vehicle weight, vehicle speed, local terrain, wheel wear, etc., the characteristics may also include characteristics of vehicles having the same axle size traveling at the same speed on the same route terrain found in the off-vehicle controller database. The measured vibration characteristics from the other vehicles may be compared to the measured vibration of the vehicle.

[0069] In step 1308, optionally, the vibration, fluid, or temperature characteristics are determined by looking at trends in the vibration, fluid, or temperature characteristics. In particular, trending a vibration characteristic may be looking at the vibration characteristic at multiple points during a trip at similar vehicle speeds to determine whether the vibration characteristic is steadily increasing, staying the same, decreasing, fluctuating, etc.

[0070] In step 1310, optionally, the vibration characteristic, fluid characteristic, or temperature characteristic is determined by comparing the characteristic measured under a first condition with the characteristic measured under a different second condition. In one example, the vibration characteristic is measured when the vehicle system is traveling at a first vehicle speed, such as 40 mph, and then measured when the vehicle system is traveling at a faster second vehicle speed, such as 60 mph.

[0071] In step 1312, optionally, vibration, fluid, or temperature characteristics are determined by comparing characteristics measured for the vehicle at a first age of the vehicle to characteristics measured for the vehicle at a second age after the vehicle. Thus, in an example, vibration characteristics of a vehicle system may be determined when the vehicle system traveled on a particular portion of a route when it was 10 years old, and when the same train made the same trip on the same route when it was 3 years old. The vibration characteristics of the vehicle system when the vehicle system was 3 years old are then compared to the vehicle system when the vehicle system was 10 years old.

[0072] In one or more embodiments, a method is provided that may include determining one or more vibration or fluid characteristics of one or more components of a vehicle and determining one or more expected characteristics for the one or more vibration or fluid characteristics. The method may also include determining whether the one or more vibration or fluid characteristics deviate from one or more expected respective characteristics and, in response to determining that the one or more vibration or fluid characteristics deviate from the one or more expected characteristics, performing one or more response actions.

[0073] Optionally, the fluid characteristic may be determined as one or more of a bearing temperature of one or more bearings of an axle of the vehicle, a motor bearing temperature measured as a bearing temperature, an oil temperature, a motor winding temperature of one or more traction motor bearings, a combined bearing temperature of one or more combined bearings, a journal bearing temperature of one or more journal bearings, a fluid temperature of one or more lubricants of a gear case or engine of the vehicle, or a winding temperature of one or more conductive windings of a motor in the vehicle. In one aspect, the one or more expected temperature characteristics that may be determined may include an expected temperature difference between bearings of different axles. In another aspect, the one or more expected temperature characteristics that are determined may include an expected motor temperature of a motor that rotates at least one axle.

[0074] Optionally, the vehicle may include multiple axles, and one or more of the vibration or fluid characteristics are determined for a first axle of the axles, and one or more expected vibration, fluid, or temperature characteristics are determined based at least in part on the operation of a set of axles not including the first axle. In one aspect, the one or more expected vibration and fluid characteristics determined may be an expected axle temperature based at least in part on the torque and temperature of each of the axles in the set. In one example, the axles may be in the same vehicle in a multi-vehicle system. In another example, the axles may be in different vehicles in a multi-vehicle system.

[0075] Optionally, vibration characteristics may be determined, including one or more of bearing vibrations of one or more bearings of an axle of the vehicle, gear vibrations of one or more gears of the vehicle, gear-borne vibrations generated by one or more gears of the vehicle, air-borne vibrations, structure-borne vibrations, case vibrations of a gear case of the vehicle, or acceleration of one or more wheels of the vehicle. In one aspect, the fluid characteristic may be a lubrication amount, including an amount of oil in one or more of an engine, a gear case, or a driveline housing in the vehicle. In one embodiment, the one or more expected characteristics may be at least partially due to ambient conditions. In one example embodiment, the ambient conditions may include one or more of the following: a rotational speed of one or more wheels of the vehicle, an ambient temperature, an ambient sound, a path characteristic of a path on which the vehicle is traveling, a vehicle characteristic of the vehicle, a torque applied to one or more axles of the vehicle, a path health, the presence of one or more gaps in the path, a curvature of the path, a position of the vehicle on the path, or an inconsistency in the path as a path characteristic, a weight of the vehicle, a moving speed of the vehicle, a size of the wheels of the vehicle, or an estimated dynamic axle weight as a vehicle characteristic.

[0076] Optionally, the one or more expected characteristics for one or more of the vibration characteristics or the fluid lubrication amount may also be based on the operation of the vehicle. In one aspect, the one or more expected characteristics may be based on the operation of the vehicle, including one or more of the following: a speed at which the vehicle is traveling, a torque exerted on an axle of the vehicle, an ambient temperature, one or more characteristics of a route on which the vehicle is traveling, or one or more characteristics of the vehicle. In one embodiment, the one or more responsive actions performed may include generating a notification to an off-vehicle facility that determines whether to repair the vehicle or modify a scheduled dispatch of the vehicle based on a deviation of one or more of the vibration characteristics or the lubrication characteristics from the one or more expected characteristics.

[0077] Optionally, the method may also include communicating the vibration characteristics to an off-vehicle system that performs one or more of: comparing the vibration characteristics of the vehicle to vibration characteristics measured for another vehicle, or trending the vibration characteristics. The method may also include communicating the vibration characteristics to an off-vehicle system that performs one or more of: comparing the vibration characteristics measured under the first conditions to vibration characteristics measured under different second conditions, or comparing the vibration characteristics measured for the vehicle at a first age of the vehicle to vibration characteristics measured for the vehicle at a second age after the vehicle. In one aspect, the one or more response actions that may be performed include de-powering a first axle of the vehicle while one or more other axles of the vehicle continue to be rotated by one or more of the vehicle's motors or engines to propel the vehicle.

[0078] Optionally, the method also includes determining a health score for each of a plurality of axles of the vehicle based on a deviation between one or more of the vibration or lubrication characteristics and the one or more expected characteristics. In one aspect, the one or more response actions that may be implemented include one or more of modifying the torque applied to one or more of the axles to depower at least one of the axles, increasing the torque applied to one or more others of the axles based on the health score, or selecting to stop movement of the vehicle. The one or more response actions that may be implemented may also include one or more of slowing movement of the vehicle, completing a current run of the vehicle, and preventing a future run of the vehicle until the vehicle is repaired, or scheduling an inspection of one or more components of the vehicle at a subsequent previously scheduled maintenance of the vehicle. In another aspect, the one or more response actions implemented may be selected based on different effects of the one or more response actions on the likelihood of completing the run. In one example, the one or more response actions implemented may include preventing modifying the torque applied to one or more of the axles in response to determining that the vehicle will stall on a grade when the torque is modified.

[0079] In one or more embodiments, a method is provided that may include determining one or more of a temperature, a vibration signature, or a fluid lubricant quantity of a first axle of a vehicle and determining one or more of a temperature, a vibration signature, or a fluid lubricant quantity of at least a second axle of the vehicle. The method may also include comparing the one or more of the temperature, vibration signature, or fluid lubricant quantity determined for the first axle to the one or more of the temperature, vibration, or fluid lubricant quantity determined for the at least the second axle, and determining a health of the first axle based on comparing the one or more of the temperature, vibration signature, or fluid lubricant quantity determined for the first axle to the one or more of the temperature, vibration signature, or fluid lubricant quantity determined for the at least the second axle.

[0080] Optionally, the vibration characteristic may be determined by a plurality of sensors coupled to different axles of the vehicle, and the method may also include comparing the vibrations measured by the sensors coupled to the different axles. The method may also include identifying the damaged portion of the path based on the vibrations measured by the sensors coupled to the different axles and compared to each other. In another aspect, one or more of the vibration characteristic or the hydrodynamic lubrication amount may be determined by direct measurement. In one example, one or more of the vibration characteristic or the hydrodynamic lubrication amount are determined by indirect measurement. In another example, one or more of the vibration characteristic or the hydrodynamic lubrication amount are determined from a measurement of another different characteristic. In another aspect, the other different characteristic includes one or more of wheel slip, current conducted in the vehicle, or capacitance measured in the vehicle. In one embodiment, the vibration characteristic is determined and includes one or more of a frequency or an amplitude of the vibration.

[0081] Optionally, the method may also include determining a comparison between one or more of the vibration characteristics or fluid lubrication amounts determined for the vehicle. The method may also include determining a comparison between one or more of the vibration characteristics or fluid lubrication amounts measured for the vehicle under different conditions or measured for another vehicle. The method may also include limiting any of the one or more response actions taken based on the comparison to eliminate false positives of faults with the vehicle.

[0082] In one or more embodiments, a system is provided that includes one or more sensors that may measure one or more vibration characteristics or fluid lubrication quantities of one or more components of a vehicle. The system may also include one or more processors that may determine one or more expected characteristics for one or more of the vibration characteristics or fluid lubrication quantities. The one or more expected characteristics may be based at least in part on ambient conditions. The one or more processors may also determine whether one or more of the vibration characteristics or lubrication characteristics deviate from the one or more expected characteristics. The one or more processors may also perform one or more response actions in response to determining that one or more of the vibration characteristics or lubrication characteristics deviate from the one or more expected characteristics.

[0083] In one or more embodiments, a method is provided that may include determining one or more of a vibration characteristic or a fluid lubrication amount of one or more components of a vehicle. The method may also include determining one or more expected characteristics for one or more of the vibration characteristic or the fluid lubrication amount. The one or more expected characteristics may be based at least in part on ambient conditions. The method may also include determining whether one or more of the vibration characteristic or the lubrication characteristic deviate from one or more expected characteristics, and determining a health score for each of a plurality of axles of the vehicle based on the deviation between one or more of the vibration characteristic or the lubrication characteristic and the one or more expected characteristics. The method may also include choosing to stop movement of the vehicle, slow down movement of the vehicle, complete a current run of the vehicle, and prevent further running of the vehicle until the vehicle is repaired, or schedule an inspection of one or more components of the vehicle at a later previously scheduled maintenance of the vehicle.

[0084] As used herein, the terms "processor" and "computer" and related terms, such as "processing device", "computing device", and "controller", may refer to, but are not limited to, those integrated circuits referred to in the art as computers, such as microcontrollers, microcomputers, programmable logic controllers (PLCs), field programmable gate arrays, and application-specific integrated circuits, as well as other programmable circuits. Suitable memory may include, for example, computer-readable media. The computer-readable media may be, for example, computer-readable non-volatile media, such as random access memory (RAM), flash memory, and the like. The term "non-transitory computer-readable media" refers to tangible computer-based devices implemented for short-term and long-term storage of information, such as computer-readable instructions, data structures, program modules and sub-modules, or other data within any device. Thus, the methods described herein may be encoded as executable instructions embodied in tangible non-transitory computer-readable media, including, but not limited to, storage devices and / or memory devices. Such instructions, when executed by a processor, cause the processor to perform at least a portion of the methods described herein. As such, the term includes tangible computer-readable media, including non-transitory computer storage, including, but not limited to, volatile and non-volatile media, as well as firmware, physical and virtual storage devices, removable and non-removable media, such as CD-ROMs, DVDs, and other digital sources such as a network or the Internet.

[0085] In one embodiment, the control system may deploy a local data collection system that may use machine learning to enable derivation-based learning outcomes. The control system may learn and make decisions from a set of data (including data provided by various sensors) by making data-driven predictions and adapting according to the set of data. In an embodiment, machine learning may include performing multiple machine learning tasks with the machine learning system, such as supervised learning, unsupervised learning, and reinforcement learning. Supervised learning may include presenting a set of example inputs and desired outputs to the machine learning system. Unsupervised learning may include a learning algorithm that structures its inputs by methods such as pattern detection and / or feature learning. Reinforcement learning may include the machine learning system performing in a dynamic environment and then providing feedback regarding correct and incorrect decisions. In an example, the machine learning may include multiple other tasks based on the output of the machine learning system. In an example, the task may be a machine learning problem such as classification, regression, clustering, density estimation, dimensionality reduction, anomaly detection, and the like. In an example, the machine learning may include multiple mathematical and statistical techniques. In examples, many types of machine learning algorithms may include decision tree based learning, association rule learning, deep learning, artificial neural networks, genetic learning algorithms, inductive logic programming, support vector machines (SVM), Bayesian networks, reinforcement learning, representation learning, rule based machine learning, sparse dictionary learning, similarity metric learning, learning classifier systems (LCS), logistic regression, random forests, K-means, gradient boosting, K nearest neighbors (KNN), a priori algorithms, etc. In embodiments, certain machine learning algorithms may be used (e.g., to solve both constrained and unconstrained optimization problems that may be based on natural selection). In examples, algorithms may be used to address mixed integer programming problems, where some components are restricted to be integer-valued. Algorithms and machine learning techniques and systems may be used in computational intelligence systems, computer vision, natural language processing (NLP), recommendation systems, reinforcement learning, building graphical models, etc.In examples, machine learning may be used for vehicle performance and behavior analysis, etc.

[0086] In one embodiment, the control system may include a policy engine that may apply one or more policies. These policies may be based at least in part on the characteristics of a given item of equipment or environment. With respect to the control policies, the neural network may receive inputs of several environmental and task-related parameters. These parameters may include an identification of a trip plan determined for the group of vehicles, data from various sensors, and location and / or position data. The neural network may be trained to generate outputs based on these inputs, the outputs representing an action or sequence of actions that the group of vehicles should take to accomplish the trip plan. During operation of an embodiment, a determination may occur by processing the inputs through the parameters of the neural network to generate a value at an output node that designates the action as a desired action. The action may be translated into a signal that causes the vehicle to operate. This may be accomplished via backpropagation, a feedforward process, closed-loop feedback, or open-loop feedback. Alternatively, rather than using backpropagation, the machine learning system of the controller may use evolutionary strategy techniques to tune various parameters of the artificial neural network. The maintenance system may use a neural network architecture with functions that may not always be solvable using backpropagation, e.g., non-convex functions. In one embodiment, the neural network has a set of parameters that represent the weights of its node connections. Several copies of this network are generated, and then various adjustments are made to the parameters and simulations are performed. Once the outputs from the various models are obtained, they can be evaluated based on their performance using a determined success metric. The best model is selected, and the vehicle controller executes a plan to achieve the desired input data to mirror the predicted best outcome scenario. Furthermore, the success metric can be a combination of optimized outcomes that can be weighted against each other.

[0087] The singular forms "a," "an," and "the" include plural references unless the context clearly indicates otherwise. "Optional" or "optionally" means that the subsequently described event or circumstance may or may not occur, and that the description may include cases where the event occurs and cases where the event does not occur. Approximation language used herein throughout this specification and claims may be applied to modify any quantitative expression that may be permissibly varied without resulting in a change in the basic function to which it may relate. Thus, values ​​modified by term(s) such as "about," "substantially," and "approximately" may not be limited to the exact value specified. In at least some instances, approximation language may correspond to the precision of an instrument for measuring the value. Throughout this specification and claims, range limitations may be combined and / or interchanged, and such ranges may be identified and include all subranges contained therein, unless the context or language dictates otherwise.

[0088] This written description uses examples to disclose the embodiments, including the best mode, and enables one of ordinary skill in the art to practice the embodiments, including making and using any devices or systems and performing any incorporated methods. The claims define the patentable scope of the disclosure, and include other examples that occur to those of ordinary skill in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that differ from the literal language of the claims, or if they include equivalent structural elements that are substantially different from the literal language of the claims.

Claims

1. 1. A method comprising: Determining one or more of vibrational, fluid, or temperature characteristics of one or more components of the vehicle; determining one or more predicted characteristics for the one or more of the vibration characteristic, the fluid characteristic, or the temperature characteristic; determining whether the one or more of the vibrational, fluid, or temperature characteristics deviate from the one or more expected respective characteristics; and performing one or more response actions in response to determining that the one or more of the vibration characteristic, the fluid characteristic, or the temperature characteristic deviates from the one or more expected characteristics.

2. 2. The method of claim 1, wherein the temperature characteristic is determined as one or more of a bearing temperature of one or more bearings of an axle of the vehicle, a motor bearing temperature of one or more traction motor bearings, a combined bearing temperature of one or more combined bearings, a journal bearing temperature of one or more journal bearings, a lubricant fluid temperature in one or more of a gear case or an engine of the vehicle, or a winding temperature of one or more conductive windings of a motor within the vehicle.

3. 3. The method of claim 2, wherein the vehicle includes a plurality of axles, the one or more of the vibration characteristic, the fluid characteristic, or the temperature characteristic are determined for a first axle of the axles, and the one or more expected vibration characteristic, fluid characteristic, or temperature characteristic are determined based at least in part on operation of a set of the axles that does not include the first axle.

4. The method of claim 3 , wherein the axles are in the same vehicle in a multi-vehicle system.

5. 2. The method of claim 1, wherein the vibration characteristics are determined and include one or more of: bearing vibration of one or more bearings of an axle of the vehicle, gear vibration of one or more gears of the vehicle, gear borne vibration generated by the one or more gears of the vehicle, air borne vibration, structure borne vibration, case vibration of a gear case of the vehicle, or acceleration of one or more wheels of the vehicle.

6. 2. The method of claim 1, wherein the one or more expected characteristics are based at least in part on ambient conditions, the ambient conditions including one or more of: a rotational speed of one or more wheels of the vehicle, an ambient temperature, ambient sound, a path characteristic of a path the vehicle is traveling on, a vehicle characteristic of the vehicle, a torque applied to one or more axles of the vehicle, a healthiness of the path, a presence of one or more gaps in the path, a curvature of the path, a position of the vehicle on the path, or an inconsistency in the path as the path characteristic, a weight of the vehicle, a speed of travel of the vehicle, a size of wheels of the vehicle, or an estimated dynamic axle weight as the vehicle characteristic.

7. 2. The method of claim 1, wherein the one or more predicted characteristics for the one or more of the vibration characteristic, the fluid characteristic, or the temperature characteristic are based on operation of the vehicle and include one or more of a speed at which the vehicle is traveling, a torque exerted on an axle of the vehicle, an ambient temperature, one or more characteristics of a path the vehicle is traveling, or one or more characteristics of the vehicle.

8. 2. The method of claim 1 , wherein the one or more response actions taken include generating a notification to an off-vehicle facility that determines whether to repair the vehicle or modify a scheduled dispatch of the vehicle based on a deviation of one or more of the vibration characteristic, the fluid characteristic, or the temperature characteristic from the one or more expected characteristics.

9. comparing the vibration characteristics of the vehicle with vibration characteristics measured for another vehicle; or Comparing the vibration characteristics measured under a first condition with vibration characteristics measured under a different second condition; or 13. The method of claim 1, further comprising: communicating the vibration characteristics to an off-vehicle system that performs one or more of the following: comparing vibration characteristics measured for the vehicle at a first age of the vehicle to vibration characteristics measured for the vehicle at a second age after the vehicle.

10. 2. The method of claim 1, further comprising determining a health score for each of a plurality of axles of the vehicle based on a deviation between the one or more of the vibration characteristic, the fluid characteristic, or the temperature characteristic and the one or more expected characteristics.

11. The one or more responsive actions to be taken are: modifying the torque applied to one or more of the axles to de-power at least one of the axles and increase the torque applied to one or more other of the axles based on the health score; or choosing to stop the movement of said vehicle; or slowing the movement of the vehicle, completing the current run of the vehicle, and preventing further runs of the vehicle until the vehicle is repaired; or and scheduling inspection of the one or more components of the vehicle at a subsequent previously scheduled maintenance of the vehicle.

12. 1. A method comprising: determining at least one first characteristic of a first axle of a vehicle, the at least one first characteristic including one or more of a temperature, a vibration signature, or a fluid lubricant amount for the first axle; determining at least one second characteristic of at least a second axle of the vehicle, the at least one second characteristic corresponding to the at least one first characteristic and including one or more of a temperature, a vibration signature, or a fluid lubricant amount for the at least the second axle; comparing the at least one first characteristic to the at least one second characteristic; determining a health of the first axle based on the comparison of the at least one first characteristic and the at least one second characteristic.

13. The vibration signature is determined by a plurality of sensors coupled to the first axle and the at least the second axle of the vehicle, and the method further comprises: comparing vibrations measured by the sensors coupled to the first axle and the at least second axle; 13. The method of claim 12, further comprising: identifying a damaged portion of a path based on the vibrations measured by the sensors coupled to the first axle and the at least the second axle and compared to each other.

14. The method of claim 12 , wherein the one or more of the vibration signature or the amount of hydrodynamic lubrication of the first axle or the second axle, respectively, are determined by direct measurement.

15. 13. The method of claim 12, wherein the one or more of the vibration signature or the amount of hydrodynamic lubrication of the respective first axle or second axle are determined from measurements of another distinct characteristic, the other distinct characteristic comprising one or more of wheel slip, current conducted within the vehicle, or capacitance measured within the vehicle.

16. (a) determining a comparison between one or more of the determined vibration signature or fluid lubrication amount of the vehicle and (b) one or more of a vibration signature or fluid lubrication amount measured for the vehicle under different conditions or measured for another vehicle; performing one or more response actions in response to determining a difference between the first characteristic and the second characteristic; The method of claim 12 , further comprising: limiting which of the one or more response actions are implemented based on the determining the comparison.

17. 1. A method comprising: Determining one or more of vibrational, fluid, or temperature characteristics of one or more components of the vehicle; determining one or more expected characteristics for the one or more of the vibration characteristic, the fluid characteristic, or the temperature characteristic, the one or more expected characteristics being based at least in part on ambient conditions; determining whether the one or more of the vibrational characteristics, the fluid characteristics, or the temperature characteristics deviate from the one or more expected characteristics; determining a health score for each of a plurality of axles of the vehicle based on a deviation between the one or more of the vibration characteristic, the fluid characteristic, or the temperature characteristic and the one or more expected characteristics; and performing at least one response action in response to the determined health score, the at least one response action including one or more of: stopping movement of the vehicle, slowing movement of the vehicle, completing a current run of the vehicle and preventing further runs of the vehicle until the vehicle is repaired, or scheduling inspection of the one or more components of the vehicle at a subsequent previously scheduled maintenance of the vehicle.

18. comparing the vibration characteristics of the vehicle with vibration characteristics measured for another vehicle; trending said vibration characteristics; Comparing the vibration characteristics measured under a first condition with the vibration characteristics measured under a second, different condition; or 20. The method of claim 17, further comprising: communicating the vibration characteristics to an off-vehicle system that performs one or more of the following: comparing the vibration characteristics measured for the vehicle at a first age of the vehicle to the vibration characteristics measured for the vehicle at a second age after the vehicle.

19. The method of claim 17 , further comprising limiting any of the one or more response actions taken based on the health score.

20. 20. The method of claim 19, wherein the one or more response actions taken also include at least one of: modifying torque applied to one or more of the axles to de-power at least one of the axles and increasing torque applied to one or more other of the axles based on the health score.

Images